Adaptec RAID 2110S U160 performance (and stability) problems

Adaptec RAID 2110S U160 performance (and stability) problems

Post by Xavier Galle » Sat, 25 May 2002 17:13:02



Hello,

        I am quite puzzled with the rather poor performance of our raid array. The array
consists of three 15k U160 hard drives (Seagate ST318452LW) on a single SCSI
bus, configured as a RAID-0 array (striping). The SCSI RAID controller is an
Adaptec SCSI RAID 2110S on a 64bit-33MHz PCI slot (Tyan AMD760-MP (not MPX)
based motherboard). The main problem is tha rather low transfer rate of the
array (80-85 MB/s reading or writing), no matter whether the array be configured
as a hardware RAID array or a software one (what follows is therefore applicable
to both types of arrays. In either case, the optimal chunk size turns out to be
128kB.

        For testing, we wrote a C program that dumps large files (2GB) in 256MB chunks.
The program uses about 256MB of memory out of 512MB available, so there is not
much room left for disk caching (roughly 130MB). Here are performance data.

1) Controler configuration

1.a SMARTROM : enable extended Int13, 16MB WB or WT cache (does not make any
difference)

1.b CONTROLER : reports a host bus transfer rate of 528MB/s while this should be
264 MB/sec (33MHz-64bits PCI instead of 66MHz). Maybee this is only a figure
aimed at showing off the controller's peak performance

1.c BUS : Ultra160, 16 bits, auto termination, 160MB/sec. Bus boot enabled.

1.d DRIVES : enabled fields are wide16, synchronous, SMART, Cmd queuing, linked
cmds, SCSI-3. 160MB/s max transfer rate, optimal status

2) OS configuration

RH Linux 7.3, kernel 2.4.18-3smp, dpt_i2o driver, ext3 filesystem

3) Performance data (sustained transfer rates)

3.a No RAID array

    - Disks tested individually : 45MB/s writing, 50 MB/s reading each disk
    - 2 disks tested simultaneously : 30MB/sec writing, 50 MB/sec reading per disk
    - 3 disks tested simultaneously : 20MB/sec writing, 30 MB/sec reading per disk

3.b RAID-0 array (3 disks, soft or hard RAID, 128kB chunk size

    - 80-85 MB/s writing or reading

As you can see, we are quite far from the 120MB/s (3/4 of 160 MB/s) one can
expect from a RAID-0 array made of 3 U160 disks, each capable of sustaining
50MB/sec, hosted by a 64bit-33MHz PCI controler. As the single disk tests show
(3.a), we suspect there is a problem on the U160 SCSI bus itself, which seems to
be completely overloaded.

Finally, we found the controller to be quite unstable because of heat problems
(even in a well-cooled case). The system indeed freezes upon extensive use of
the SCSI disks (which by the way are in a separate case) and controller unless
the PC case is left open.

How can we help improve the performance of this RAID array ?

Best Regards,

        Xavier
--

===========================================================
Dr. Xavier Gallez
Aeroacoustics Research Engineer
Free Field Technologies SA
Place de l'Universit, 16
1348 Louvain-la-Neuve
Belgium
Tel: +32-10-451 226
Fax: +32-10-454 626

URLs: http://www.fft.be, http://web.wanadoo.be/xaviergallez
===========================================================

 
 
 

Adaptec RAID 2110S U160 performance (and stability) problems

Post by Mari » Sun, 26 May 2002 04:05:40


check the update kernel 2.4.18-3smp not i686 but athlon
we'll talk about then

> Hello,

>     I am quite puzzled with the rather poor performance of our raid
> array. The array consists of three 15k U160 hard drives (Seagate
> ST318452LW) on a single SCSI bus, configured as a RAID-0 array
> (striping). The SCSI RAID controller is an Adaptec SCSI RAID 2110S on a
> 64bit-33MHz PCI slot (Tyan AMD760-MP (not MPX) based motherboard). The
> main problem is tha rather low transfer rate of the array (80-85 MB/s
> reading or writing), no matter whether the array be configured as a
> hardware RAID array or a software one (what follows is therefore
> applicable to both types of arrays. In either case, the optimal chunk
> size turns out to be 128kB.

>     For testing, we wrote a C program that dumps large files (2GB) in
> 256MB chunks. The program uses about 256MB of memory out of 512MB
> available, so there is not much room left for disk caching (roughly
> 130MB). Here are performance data.

> 1) Controler configuration

> 1.a SMARTROM : enable extended Int13, 16MB WB or WT cache (does not make
> any difference)

> 1.b CONTROLER : reports a host bus transfer rate of 528MB/s while this
> should be 264 MB/sec (33MHz-64bits PCI instead of 66MHz). Maybee this is
> only a figure aimed at showing off the controller's peak performance

> 1.c BUS : Ultra160, 16 bits, auto termination, 160MB/sec. Bus boot enabled.

> 1.d DRIVES : enabled fields are wide16, synchronous, SMART, Cmd queuing,
> linked cmds, SCSI-3. 160MB/s max transfer rate, optimal status

> 2) OS configuration

> RH Linux 7.3, kernel 2.4.18-3smp, dpt_i2o driver, ext3 filesystem

> 3) Performance data (sustained transfer rates)

> 3.a No RAID array

>    - Disks tested individually : 45MB/s writing, 50 MB/s reading each disk
>    - 2 disks tested simultaneously : 30MB/sec writing, 50 MB/sec reading
> per disk
>    - 3 disks tested simultaneously : 20MB/sec writing, 30 MB/sec reading
> per disk

> 3.b RAID-0 array (3 disks, soft or hard RAID, 128kB chunk size

>    - 80-85 MB/s writing or reading

> As you can see, we are quite far from the 120MB/s (3/4 of 160 MB/s) one
> can expect from a RAID-0 array made of 3 U160 disks, each capable of
> sustaining 50MB/sec, hosted by a 64bit-33MHz PCI controler. As the
> single disk tests show (3.a), we suspect there is a problem on the U160
> SCSI bus itself, which seems to be completely overloaded.

> Finally, we found the controller to be quite unstable because of heat
> problems (even in a well-cooled case). The system indeed freezes upon
> extensive use of the SCSI disks (which by the way are in a separate
> case) and controller unless the PC case is left open.

> How can we help improve the performance of this RAID array ?

> Best Regards,

>     Xavier


 
 
 

Adaptec RAID 2110S U160 performance (and stability) problems

Post by Dennis Gerasimo » Thu, 06 Jun 2002 13:23:19



> Hello,

>     I am quite puzzled with the rather poor performance of our raid
> array. The array consists of three 15k U160 hard drives (Seagate
> ST318452LW) on a single SCSI bus, configured as a RAID-0 array
> (striping). The SCSI RAID controller is an Adaptec SCSI RAID 2110S on a
> 64bit-33MHz PCI slot (Tyan AMD760-MP (not MPX) based motherboard). The
> main problem is tha rather low transfer rate of the array (80-85 MB/s
> reading or writing), no matter whether the array be configured as a
> hardware RAID array or a software one (what follows is therefore
> applicable to both types of arrays. In either case, the optimal chunk
> size turns out to be 128kB.

>     For testing, we wrote a C program that dumps large files (2GB) in
> 256MB chunks. The program uses about 256MB of memory out of 512MB
> available, so there is not much room left for disk caching (roughly
> 130MB). Here are performance data.

> 1) Controler configuration

> 1.a SMARTROM : enable extended Int13, 16MB WB or WT cache (does not make
> any difference)

> 1.b CONTROLER : reports a host bus transfer rate of 528MB/s while this
> should be 264 MB/sec (33MHz-64bits PCI instead of 66MHz). Maybee this is
> only a figure aimed at showing off the controller's peak performance

> 1.c BUS : Ultra160, 16 bits, auto termination, 160MB/sec. Bus boot enabled.

> 1.d DRIVES : enabled fields are wide16, synchronous, SMART, Cmd queuing,
> linked cmds, SCSI-3. 160MB/s max transfer rate, optimal status

> 2) OS configuration

> RH Linux 7.3, kernel 2.4.18-3smp, dpt_i2o driver, ext3 filesystem

> 3) Performance data (sustained transfer rates)

> 3.a No RAID array

>    - Disks tested individually : 45MB/s writing, 50 MB/s reading each disk
>    - 2 disks tested simultaneously : 30MB/sec writing, 50 MB/sec reading
> per disk
>    - 3 disks tested simultaneously : 20MB/sec writing, 30 MB/sec reading
> per disk

> 3.b RAID-0 array (3 disks, soft or hard RAID, 128kB chunk size

>    - 80-85 MB/s writing or reading

> As you can see, we are quite far from the 120MB/s (3/4 of 160 MB/s) one
> can expect from a RAID-0 array made of 3 U160 disks, each capable of
> sustaining 50MB/sec, hosted by a 64bit-33MHz PCI controler. As the
> single disk tests show (3.a), we suspect there is a problem on the U160
> SCSI bus itself, which seems to be completely overloaded.

> Finally, we found the controller to be quite unstable because of heat
> problems (even in a well-cooled case). The system indeed freezes upon
> extensive use of the SCSI disks (which by the way are in a separate
> case) and controller unless the PC case is left open.

> How can we help improve the performance of this RAID array ?

I do not think you can improve this situation dramatically. First of all
it is quite normal to see such a progression (or rather, regression) of
speed vs number of drives. You have to remember that they are all using
the same PCI bus, and SCSI bus. Besides, total of 85MB/sec is not that
bad on 3 drives, IMHO. Anothe issue is measuring the speed. It is quite
tricky. If you push enough commands into tagged queue, then you might
see better results. But then again, in real life you will get much worse
  numbers anyway.
The card you are mentioning is a low-end card. From adaptec. Please,
dont shoot me, but when comparing side by side in identical setups with
LSI logic, adaptec is low-end even if you pay 4x the price.
I would suggest getting a different controller. If you have enough CPU
to spare, then a software-based RAID coupled with a really good SCSI
card, like dual channel 83c1010 (see LSI22915A) will probably do a much
better job.

--
Dennis

TMI: Affordable RAID subsystems
with multiple interface types:
http://www.technomagesinc.com

 
 
 

1. Adaptec RAID 2110S on which /dev ?

Hi there,

        I have RAID-0 array of 4 (18GB) disks managed by an Adaptec SCSI RAID 2110S
controller. Disks' SCSI ids range from 0 to 3, Linux OS is RH 7.3 w/ kernel
2.4.18-3 smp (provided w/ the RH 7.3 distribution). Upon booting after the
installation of the RAID controller, RH recognizes the controller and seems to
load the driver for it. Then, the raid array appears to be /dev/sda which, after
fdisk /dev/sda1 + mkfs.ext3 /dev/sda1 + mount looks like a single 4*18GB
(approximately) disk. I am wondering why the raid array is recognized as
/dev/sda, not /dev/rd/c0d0 or a similar device. Is it really working properly ?

Best Regards,

        Xavier

===========================================================
Dr. Xavier Gallez
Aeroacoustics Research Engineer
Free Field Technologies SA
Place de l'Universit, 16
1348 Louvain-la-Neuve
Belgium
Tel: +32-10-451 226
Fax: +32-10-454 626

URLs: http://www.fft.be, http://web.wanadoo.be/xaviergallez
===========================================================

2. 33.6kbps Fax/Modem PCMCIA

3. Adaptec SCSI Raid 2110s

4. IMAP & Kiss of death

5. Adaptec 2100S Single Channel U160 Raid Controller and 2.4 kernel feedback

6. 36Gig UDMA66 Maxtor with Promise66

7. aic7xxx driver error at boot for Adaptec AIC-7899P U160

8. Looking for sites with information about free software

9. U160 on Adaptec 39160

10. very poor performance / throughput with adaptec / mylex scsi raid controllers

11. Adaptec u160 29160N Support?

12. Adaptec 2940 and filesystem stability problems

13. TCP/IP Stability & Performance: Linux vs FreeBSD